This is workflow infrastructure for managing multi-step work that spans sessions or touches more than three files. It enforces a living document format with sections for progress tracking, surprises, decisions, and validation commands. The format is deliberately narrative, not a checklist: it captures why changes matter, what the codebase looks like now, and how to prove success. The real discipline is updating progress immediately after each milestone with timestamps, because that's your only persistence between sessions. Plans live in docs/exec-plans/active until complete, then move to completed. If you're doing anything non-trivial, this keeps you from redoing work or losing context when you pick it back up tomorrow.

skills.sh installs
232
GitHub stars
222
last updated
Aug 21, 2026

Install

$ npx -y skills add pproenca/dot-skills --skill exec-plan --agent claude-code

Installs into .claude/skills of the current project.

Files

ExecPlan — Lifecycle Management

Announce at start: "Using the exec-plan skill."

What is an ExecPlan

A self-contained, living document that a fresh agent session can follow to deliver observable, working behavior. Lives in docs/exec-plans/. The format follows the specification in docs/PLANS.md.

An ExecPlan is NOT a todo list. It is a narrative that tells the story of a change: why it matters, what the codebase looks like now, what it should look like after, and how to prove it worked.

When to use this skill

  • Required for multi-step or multi-file work, new features, refactors, or tasks expected to take more than about an hour.
  • Optional for trivial fixes, but if you skip it for a substantial task, state the reason.
  • Always when resuming work from a previous session.

The Three Modes

Mode 1: CREATE a new plan

When starting new multi-step work:

Sponsors

Details

Repository
github.com/pproenca/dot-skills
Categories
Code Review & Quality, Productivity & Planning
First seen
Jun 3, 2026

More from pproenca/dot-skills

All 100
1borghei avatarsenior-qaborghei/claude-skillsTesting for React/Next.js with Jest, React Testing Library, and Playwright. Use when generating tests, writing unit tests, analyzing coverage, scaffolding E2E t230skills.sh installs
2casper-studios avatarsend-to-linearcasper-studios/casper-marketplaceExtract actionable Linear tickets from ambiguous input — Slack conversations, call transcripts, screenshots, meeting notes, or any unstructured material. Propos228skills.sh installs
3anthropics avatardata-explorationanthropics/knowledge-work-pluginsProfile and explore datasets to understand their shape, quality, and patterns before analysis. Use when encountering a new dataset, assessing data quality, disc227skills.sh installs
4manojbajaj95 avatarutm-buildermanojbajaj95/claude-gtm-pluginGenerate UTM-tagged URLs for campaign tracking. Create consistent, organized tracking links for Google Analytics, HubSpot, and other analytics platforms. Suppor227skills.sh installs
5yonatangross avatarreact-server-components-frameworkyonatangross/orchestkitUse when building Next.js 16+ apps with React Server Components. Covers App Router, Cache Components (replacing experimental_ppr), streaming SSR, Server Actions227skills.sh installs
6massgen avatarmassgenmassgen/skillsInvoke MassGen's multi-agent system. Use when the user wants multiple AI agents on a task: writing, code, review, planning, specs, research, design, or any task226skills.sh installs